Saved in:
Bibliographic Details
Main Authors: Buskulic, Nathan, Fadil, Jalal, Quéau, Yvain
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.02986
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Solving inverse problems with neural networks benefits from very few theoretical guarantees when it comes to the recovery guarantees. We provide in this work convergence and recovery guarantees for self-supervised neural networks applied to inverse problems, such as Deep Image/Inverse Prior, and trained with inertia featuring both viscous and geometric Hessian-driven dampings. We study both the continuous-time case, i.e., the trajectory of a dynamical system, and the discrete case leading to an inertial algorithm with an adaptive step-size. We show in the continuous-time case that the network can be trained with an optimal accelerated exponential convergence rate compared to the rate obtained with gradient flow. We also show that training a network with our inertial algorithm enjoys similar recovery guarantees though with a less sharp linear convergence rate.